[WIP] Fix batching in DIG

[gsarti]

Description

Fixes #113

Type of Change

🔧 Bug fix (non-breaking change which fixes an issue)

[gsarti]

Current status:

• DIG attribution was made compatible with newer changes (decoder-only model support, etc.) and supports both source and source-target attribution.
• The problematic behavior of inconsistent outputs when testing the same input alone vs. inside a batch persist. The issue is probably in the scale_input function call inside DiscretizedIntegratedGradient.attribute, since the rest is mostly compatible with the original IG attribution.
• Open question: is return_convergence_delta meaningful in this setting? First thoughts: it could provide information on the distance from a good non-orthogonal path, but should not be used as in IG.